turboderp/GLM-4.6-exl3-2.33bpw-opt

🤗 Hugging Face sourcetext-generationmit52.3B params105 GBsafetensorsHF checksums availableupdated today
No torrent yet

2.33 bpw EXL3 quant of GLM-4.6

Base quants provided by MikeRoz

This is just a quick mix of the 2.25 bpw quant with attention, dense layers and shared experts in 4.0 bpw.